未遵循指令 失败
看看哪些 AI 模型最常遇到 未遵循指令，让你在选择前先发现稳定性风险。 排序方式: 总成本 ↑.
215/215
筛选模型
没有模型匹配当前搜索和筛选条件。
| 排名 | 模型 | 公司 | 未遵循指令 次数 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #131 | Grok 4.3 medium | X AI | 2 | 7.0 | $0.741 | 12/22 | 44.2s |
| #145 | Qwen3.6 Flash medium | Qwen | 1 | 6.8 | $0.741 | 12/22 | 45.0s |
| #201 | Grok 4.20 Beta medium | X AI | 1 | 6.0 | $0.750 | 14/18 | 9.75s |
| #194 | Trinity Large Thinking medium | Arcee AI | 4 | 6.1 | $0.756 | 8/22 | 85.4s |
| #86 | Seed-2.0-Code low | Bytedance Seed | 1 | 7.7 | $0.767 | 13/22 | 72.2s |
| #102 | GPT-5.4 Mini medium | OpenAI | 3 | 7.5 | $0.786 | 12/22 | 26.7s |
| #137 | Grok 4.20 medium | X AI | 2 | 7.0 | $0.805 | 11/22 | 32.6s |
| #60 | Claude Sonnet 5 medium | Anthropic | 1 | 8.2 | $0.922 | 15/22 | 12.5s |
| #100 | Qwen3.5-27B medium | Qwen | 2 | 7.5 | $0.982 | 13/22 | 113.3s |
| #30 | GPT-5.3-Codex medium | OpenAI | 2 | 8.9 | $0.988 | 16/22 | 16.9s |
| #64 | Inkling high | Thinkingmachines | 1 | 8.0 | $1.046 | 15/22 | 62.6s |
| #147 | Seed-2.0-Code medium | Bytedance Seed | 1 | 6.8 | $1.153 | 10/22 | 101.1s |
| #120 | Claude Opus 4.8 none | Anthropic | 1 | 7.3 | $1.166 | 13/22 | 4.92s |
| #52 | GPT-5.2 medium | OpenAI | 3 | 8.4 | $1.182 | 14/22 | 28.5s |
| #68 | GLM 5.2 high | Z.ai | 1 | 8.0 | $1.188 | 14/22 | 69.9s |